# Feedforward semantic segmentation with zoom-out features

arXiv: https://arxiv.org/abs/1412.0774 · HTML: https://mlsanity.com/paper/1412.0774/

## Key facts

- Cited by 21 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 2 Dec 2014.

## Built on by (most cited first, 21 of 21)

- [Unsupervised Hierarchical Semantic Segmentation with Multiview Cosegmentation and Clustering Transformers](https://mlsanity.com/paper/2204.11432/) (2022)
- [Structural and Statistical Texture Knowledge Distillation for Semantic Segmentation](https://mlsanity.com/paper/2305.03944/) (2023)
- [ProtoSeg: Interpretable Semantic Segmentation with Prototypical Parts](https://mlsanity.com/paper/2301.12276/) (2023)
- [Semantic Image Segmentation: Two Decades of Research](https://mlsanity.com/paper/2302.06378/) (2023)
- [Large Separable Kernel Attention: Rethinking the Large Kernel Attention Design in CNN](https://mlsanity.com/paper/2309.01439/) (2023)
- [Neural Neighbor Style Transfer](https://mlsanity.com/paper/2203.13215/) (2022)
- [The Overlooked Classifier in Human-Object Interaction Recognition](https://mlsanity.com/paper/2112.06392/) (2021)
- [Multi-Class Segmentation from Aerial Views using Recursive Noise Diffusion](https://mlsanity.com/paper/2212.00787/) (2022)
- [Superevents: Towards Native Semantic Segmentation for Event-based Cameras](https://mlsanity.com/paper/2105.06091/) (2021)
- [Superpixel-based Refinement for Object Proposal Generation](https://mlsanity.com/paper/2101.04574/) (2021)
- [MoE-SPNet: A Mixture-of-Experts Scene Parsing Network](https://mlsanity.com/paper/1806.07049/) (2018)
- [FaceRefiner: High-Fidelity Facial Texture Refinement with Differentiable Rendering-based Style Transfer](https://mlsanity.com/paper/2601.04520/) (2026)
- [Learning Class-Agnostic Pseudo Mask Generation for Box-Supervised Semantic Segmentation](https://mlsanity.com/paper/2103.05463/) (2021)
- [A Novel Upsampling and Context Convolution for Image Semantic Segmentation](https://mlsanity.com/paper/2103.11110/) (2021)
- [Fast whole-slide cartography in colon cancer histology using superpixels and CNN classification](https://mlsanity.com/paper/2106.15893/) (2021)
- [Border-SegGCN: Improving Semantic Segmentation by Refining the Border Outline using Graph Convolutional Network](https://mlsanity.com/paper/2109.05353/) (2021)
- [Leveraging Adaptive Implicit Representation Mapping for Ultra High-Resolution Image Segmentation](https://mlsanity.com/paper/2407.21256/) (2024)
- [Detecting and Segmenting Adversarial Graphics Patterns from Images](https://mlsanity.com/paper/2108.09383/) (2021)
- [The Overlooked Classifier in Human-Object Interaction Recognition](https://mlsanity.com/paper/2203.05676/) (2022)
- [Data-centric AI approach to improve optic nerve head segmentation and localization in OCT en face images](https://mlsanity.com/paper/2208.03868/) (2022)
- [Your Image is My Video: Reshaping the Receptive Field via Image-To-Video Differentiable AutoAugmentation and Fusion](https://mlsanity.com/paper/2403.15194/) (2024)

## Abstract (arXiv)

We introduce a purely feed-forward architecture for semantic segmentation. We map small image elements (superpixels) to rich feature representations extracted from a sequence of nested regions of increasing extent. These regions are obtained by "zooming out" from the superpixel all the way to scene-level resolution. This approach exploits statistical structure in the image and in the label space without setting up explicit structured prediction mechanisms, and thus avoids complex and expensive inference. Instead superpixels are classified by a feedforward multilayer network. Our architecture achieves new state of the art performance in semantic segmentation, obtaining 64.4% average accuracy on the PASCAL VOC 2012 test set.